Explainable Load Forecasting with Covariate-Informed Time Series Foundation Models

Matthias Hertel, Alexandra Nikoltchovska, Sebastian Pütz, Ralf Mikut, Benjamin Schäfer et al.|April 30, 2026arXiv

Key Takeaway

You can now explain time series foundation model predictions efficiently using SHAP, making them trustworthy for critical infrastructure like power grids—without sacrificing accuracy or requiring model retraining.

Summary

This paper makes time series foundation models (TSFMs) transparent for power grid forecasting by developing an efficient method to compute SHAP explanations. The approach leverages TSFMs' ability to handle variable input lengths and selective masking, enabling scalable explanations without retraining.

applications evaluation

Key Terms

shapley-values foundation-models covariate-shift zero-shot-learning